← Latest products

onprem unstructured data extraction with 4 lines of code

An on-premises, OCR-free unstructured data extraction, markdown conversion and benchmarking toolkit. (https://idp-leaderboard.org/). The traditional pipeline for unstructured data extraction typically follows these steps: 1.

Open source

2,087 stars · GitHubexternal site

Visit github.comexternal site

Reactions (1)

Similar products

by description similarity

  1. Open-Source Document Extraction Tool

    github.com

    Open-source spreadsheets platform for deep research and document processing

    Hacker News13 pts

  2. We have built an API to extract data from unstructured documents

    extracta.ai

    Hacker News11 pts

  3. Extractous

    github.com

    Rust based data extraction ~25x faster than unstructured-io

    Hacker News6 pts

  4. udoc. Dependency-free document extraction in Rust

    newelh.github.io

    A unified document extraction toolkit -- text, tables, and rendered pages from PDF, DOCX, XLSX, PPTX, ODF, RTF, and Markdown.

    Hacker News5 pts

  5. Data Extraction with Flexible Schemas

    go.sea.dev

    We’ve built a data extraction tool to flexibly automate data and document processing.

    Hacker News5 pts